# Text Generation Models, Page 25: Open-Weight AI Source: https://savrn.com/models/tasks/text-generation/page/25 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- SAVRN Model Hub · Models by Task # Text Generation Models 1,582 open-weight text generation models in the SAVRN Model Hub, with Convergent Intelligence, Qwen and Francesca Padovani publishing the most. 1,582Models 732Publishers 107K to 1.7TParameter range 8Licenses ## SAVRN's Take Text generation is where most of the attention goes, and where most of the money is spent. The models on this page run from tiny research checkpoints that fit on a laptop to frontier-class systems that need a full server of accelerators. The first question we ask about any of them is not how smart it is, but what it costs to keep it answering around the clock. That cost comes down to three things: the size of the weights, the precision you run them at, and how much context each request carries. Moving from 16-bit to 4-bit cuts the memory a model needs by roughly four times, which is often the difference between one server and several. Mixture-of-experts models, such as the newer DeepSeek, Qwen and Nemotron releases, hold a large total parameter count but activate only a small share per token, so they answer faster than their size suggests while still needing the memory to hold every expert. Licensing decides the rest. Apache 2.0 and MIT models can go straight into a commercial product. Llama, Gemma's earlier generations and models marked other each carry terms you need to read first, and a model with no stated license is research material until the publisher says otherwise. Our advice is to shortlist by license, size to the hardware you can actually run, then test the survivors on your own prompts. The table below is sorted by what people download, not by what we recommend. SAVRN Research, 2026-09-18 ## Most Downloaded | Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit | | --- | --- | --- | --- | --- | --- | | [Qwen3-0.6B](https://savrn.com/models/qwen3-0-6b) | Qwen | 752M | apache-2.0 | 25.2M | 1x MI300X, $1.85/hr | | [gpt2](https://savrn.com/models/gpt2) | OpenAI community | 137M | mit | 18.8M | 1x MI300X, $1.85/hr | | [Qwen3-4B](https://savrn.com/models/qwen3-4b) | Qwen | 4B | apache-2.0 | 11.4M | 1x MI300X, $1.85/hr | | [Qwen3-14B](https://savrn.com/models/qwen3-14b) | Qwen | 14.8B | apache-2.0 | 9.4M | 1x MI300X, $1.85/hr | | [Qwen3-8B](https://savrn.com/models/qwen3-8b) | Qwen | 8.2B | apache-2.0 | 8.1M | 1x MI300X, $1.85/hr | | [Qwen2.5-7B-Instruct](https://savrn.com/models/qwen2-5-7b-instruct) | Qwen | 7.6B | apache-2.0 | 6.4M | 1x MI300X, $1.85/hr | | [gpt-oss-20b](https://savrn.com/models/gpt-oss-20b) | OpenAI | 20.9B | apache-2.0 | 5.7M | 1x MI300X, $1.85/hr | | [opt-125m](https://savrn.com/models/opt-125m) | AI at Meta | — | other | 5.6M | — | | [DeepSeek-V3.2](https://savrn.com/models/deepseek-v3-2) | DeepSeek | 685.4B | mit | 5.4M | 7x MI325X, $14.00/hr | | [Qwen2.5-0.5B-Instruct](https://savrn.com/models/qwen2-5-0-5b-instruct) | Qwen | 494M | apache-2.0 | 5.3M | 1x MI300X, $1.85/hr | ## Licenses | License | Models | Commercial use | | --- | --- | --- | | [apache-2.0](https://savrn.com/models/licenses/apache-2-0) | 734 | Yes | | not stated | 345 | Not stated | | other | 175 | Read the license | | [mit](https://savrn.com/models/licenses/mit) | 152 | Yes | | [cc-by-nc-4.0](https://savrn.com/models/licenses/cc-by-nc-4-0) | 42 | Not without separate permission | | [llama3.2](https://savrn.com/models/licenses/llama3-2) | 33 | Read the license | | [gemma](https://savrn.com/models/licenses/gemma) | 22 | Yes, with conditions | | [llama3.1](https://savrn.com/models/licenses/llama3-1) | 21 | Yes, with conditions | ## Who Publishes Them | Publisher | Models | | --- | --- | | [Convergent Intelligence](https://savrn.com/model-publishers/reaperdoesntknow) | 54 | | [Qwen](https://savrn.com/model-publishers/qwen) | 42 | | [Francesca Padovani](https://savrn.com/model-publishers/francesca9805) | 37 | | [Yanggangu](https://savrn.com/model-publishers/yanggangu) | 28 | | [Shreyansh singh](https://savrn.com/model-publishers/shreyansh12183) | 25 | | [Kumar](https://savrn.com/model-publishers/sandeep123) | 23 | ## All 1,582 Models, Page 25 of 27 Model · Text generation ### [stride-qwen3-4b-stabilized-2048-token_uniform-20260916](https://savrn.com/models/stride-qwen3-4b-stabilized-2048-token-uniform-20260916) [Kumar](https://savrn.com/model-publishers/sandeep123) STRIDE ablation distributing each response diversity bonus uniformly over its eligible tokens. Training explicitly renders enablethinking=False, recorded as thinkingmode: false in the scientific contract. The pinned tokenizer and chat template remain unchanged. Use the same explicit keyword at inference, particularly for Qwen3-1.7B, whose default template enables thinking. Every checkpoint in this repository requires explicit nonthinking provenance. This public repository retains every published optimizer-update adapter, including update zero (the initial, untrained adapter). Training is planned for 4 epochs on the same 2,048-question training split as the earlier STRIDE runs. The global… Open weights peft [View model](https://savrn.com/models/stride-qwen3-4b-stabilized-2048-token-uniform-20260916) Model · Text generation ### [SUPERBRAIN-1](https://savrn.com/models/superbrain-1) [Ahmad Odeh](https://savrn.com/model-publishers/abuz8studios) SUPERBRAIN-1 is a 9B Arabic model by ABUZ8, fine-tuned from QCRI/Fanar-1-9B to do Arabic root, conjugate, derive masdars and participles, and name a verb's form. It is a completion model, not a chat model: give it one of the prompt formats below and read the first line of the output. Packet B — held-out test. 1,343 items over 258 roots that were Quranic Arabic Corpus) and modern words from the Arramooz lexicon. Root items are asked both with a few-shot prompt and as a bare question. Root accuracy by root class (bare): sound 79%, hollow 60%, doubled 56%, hamzated 51%, defective 45%, assimilated 44%. 85-item gate (v3) — 50 root words, 20 arithmetic/logic questions, 15 Generalization probe.… Open weights apache-2.0 gguf [View model](https://savrn.com/models/superbrain-1) Model · Text generation ### [svd-safety-l2_jbbpure_ka1_a1p0_free_remove40](https://savrn.com/models/svd-safety-l2-jbbpure-ka1-a1p0-free-remove40) [Park](https://savrn.com/model-publishers/jeesup) A Llama-2-7b-chat checkpoint compressed with SVD-LLM to 60.0% of dense parameters, then given a 0.0% parameter budget of restored SVD components selected by the unknown rule. This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-2-7b-chat: compression alone raises attack-success rate, and the point of the study is to quantify that and test recovery. Treat… Open weights llama2 6.7B parameters 4,096 tokens transformers [View model](https://savrn.com/models/svd-safety-l2-jbbpure-ka1-a1p0-free-remove40) Model · Text generation ### [svd-safety-l2_remove40_swapgapiter_rankunit_b010](https://savrn.com/models/svd-safety-l2-remove40-swapgapiter-rankunit-b010) [Park](https://savrn.com/model-publishers/jeesup) A Llama-2-7b-chat checkpoint compressed with SVD-LLM to 60.0% of dense parameters, then edited by 10 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-2-7b-chat: compression alone raises attack-success… Open weights llama2 6.7B parameters 4,096 tokens transformers [View model](https://savrn.com/models/svd-safety-l2-remove40-swapgapiter-rankunit-b010) Model · Text generation ### [svd-safety-l3_remove40_swapgapiter_b010](https://savrn.com/models/svd-safety-l3-remove40-swapgapiter-b010) [Park](https://savrn.com/model-publishers/jeesup) A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 60.0% of dense parameters, then edited by 10 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises… Open weights llama3 8B parameters 8,192 tokens transformers [View model](https://savrn.com/models/svd-safety-l3-remove40-swapgapiter-b010) Model · Text generation ### [svd-safety-l3_remove40_swapgapiter_b010_r08](https://savrn.com/models/svd-safety-l3-remove40-swapgapiter-b010-r08) [Park](https://savrn.com/model-publishers/jeesup) A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 60.0% of dense parameters, then edited by 8 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises… Open weights llama3 8B parameters 8,192 tokens transformers [View model](https://savrn.com/models/svd-safety-l3-remove40-swapgapiter-b010-r08) Model · Text generation ### [svd-safety-l3_remove40_swapgapiter_b010_r09](https://savrn.com/models/svd-safety-l3-remove40-swapgapiter-b010-r09) [Park](https://savrn.com/model-publishers/jeesup) A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 60.0% of dense parameters, then edited by 9 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises… Open weights llama3 8B parameters 8,192 tokens transformers [View model](https://savrn.com/models/svd-safety-l3-remove40-swapgapiter-b010-r09) Model · Text generation ### [svd-safety-l3_remove50_swapgapiter_b010_r01](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-b010-r01) [Park](https://savrn.com/model-publishers/jeesup) A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 1 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises… Open weights llama3 8B parameters 8,192 tokens transformers [View model](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-b010-r01) Model · Text generation ### [svd-safety-l3_remove50_swapgapiter_b010_r02](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-b010-r02) [Park](https://savrn.com/model-publishers/jeesup) A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 2 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises… Open weights llama3 8B parameters 8,192 tokens transformers [View model](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-b010-r02) Model · Text generation ### [svd-safety-l3_remove50_swapgapiter_b010_r03](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-b010-r03) [Park](https://savrn.com/model-publishers/jeesup) A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 3 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises… Open weights llama3 8B parameters 8,192 tokens transformers [View model](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-b010-r03) Model · Text generation ### [svd-safety-l3_remove50_swapgapiter_b010_r04](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-b010-r04) [Park](https://savrn.com/model-publishers/jeesup) A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 4 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises… Open weights llama3 8B parameters 8,192 tokens transformers [View model](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-b010-r04) Model · Text generation ### [svd-safety-l3_remove50_swapgapiter_b010_r05](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-b010-r05) [Park](https://savrn.com/model-publishers/jeesup) A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 5 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises… Open weights llama3 8B parameters 8,192 tokens transformers [View model](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-b010-r05) Model · Text generation ### [svd-safety-l3_remove50_swapgapiter_b010_r06](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-b010-r06) [Park](https://savrn.com/model-publishers/jeesup) A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 6 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises… Open weights llama3 8B parameters 8,192 tokens transformers [View model](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-b010-r06) Model · Text generation ### [svd-safety-l3_remove50_swapgapiter_b010_r07](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-b010-r07) [Park](https://savrn.com/model-publishers/jeesup) A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 7 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises… Open weights llama3 8B parameters 8,192 tokens transformers [View model](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-b010-r07) Model · Text generation ### [svd-safety-l3_remove50_swapgapiter_b010_r08](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-b010-r08) [Park](https://savrn.com/model-publishers/jeesup) A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 8 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises… Open weights llama3 8B parameters 8,192 tokens transformers [View model](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-b010-r08) Model · Text generation ### [svd-safety-l3_remove50_swapgapiter_evfront_b010](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-evfront-b010) [Park](https://savrn.com/model-publishers/jeesup) A Llama-3-8B-Instruct checkpoint compressed with SVD-LLM to 50.0% of dense parameters, then edited by 10 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-3-8B-Instruct: compression alone raises… Open weights llama3 8B parameters 8,192 tokens transformers [View model](https://savrn.com/models/svd-safety-l3-remove50-swapgapiter-evfront-b010) Model · Text generation ### [svd-safety-mis7_swift_remove30_swapgapiter_b010](https://savrn.com/models/svd-safety-mis7-swift-remove30-swapgapiter-b010) [Park](https://savrn.com/model-publishers/jeesup) A Mistral-7B-Instruct-v0.2 checkpoint compressed with SVD-LLM to 70.0% of dense parameters, then edited by 10 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Mistral-7B-Instruct-v0.2: compression alone… Open weights apache-2.0 7.2B parameters 32,768 tokens transformers [View model](https://savrn.com/models/svd-safety-mis7-swift-remove30-swapgapiter-b010) Model · Text generation ### [swa-100mb-after-wc-loglinear-newlex-before-ckpt500-packed-bfdiso_seed3407](https://savrn.com/models/swa-100mb-after-wc-loglinear-newlex-before-ckpt500-packed-bfdiso-seed3407) [Francesca Padovani](https://savrn.com/model-publishers/francesca9805) This model is a fine-tuned version of francesca9805/ppt-wc-loglinear-newlex-swa-before-100mb-packed-bfdisoseed3407. It has been trained using TRL. This model was trained with SFT. Open weights 125M parameters transformers [View model](https://savrn.com/models/swa-100mb-after-wc-loglinear-newlex-before-ckpt500-packed-bfdiso-seed3407) Model · Text generation ### [swa-latn-100mb-ppt-Dp-100mb-packed-bfd_seed10](https://savrn.com/models/swa-latn-100mb-ppt-dp-100mb-packed-bfd-seed10) [Francesca Padovani](https://savrn.com/model-publishers/francesca9805) This model is a fine-tuned version of goldfish-models/swalatn100mb. It has been trained using TRL. This model was trained with SFT. Open weights 125M parameters transformers [View model](https://savrn.com/models/swa-latn-100mb-ppt-dp-100mb-packed-bfd-seed10) Model · Text generation ### [swa-latn-100mb-ppt-Dp-100mb-packed-bfd_seed3407](https://savrn.com/models/swa-latn-100mb-ppt-dp-100mb-packed-bfd-seed3407) [Francesca Padovani](https://savrn.com/model-publishers/francesca9805) This model is a fine-tuned version of goldfish-models/swalatn100mb. It has been trained using TRL. This model was trained with SFT. Open weights 125M parameters transformers [View model](https://savrn.com/models/swa-latn-100mb-ppt-dp-100mb-packed-bfd-seed3407) Model · Text generation ### [swa-latn-100mb-ppt-Dp-100mb-packed-bfd_seed455](https://savrn.com/models/swa-latn-100mb-ppt-dp-100mb-packed-bfd-seed455) [Francesca Padovani](https://savrn.com/model-publishers/francesca9805) This model is a fine-tuned version of goldfish-models/swalatn100mb. It has been trained using TRL. This model was trained with SFT. Open weights 125M parameters transformers [View model](https://savrn.com/models/swa-latn-100mb-ppt-dp-100mb-packed-bfd-seed455) Model · Text generation ### [swa-latn-100mb-ppt-Dp-10mb-packed-bfd_seed10](https://savrn.com/models/swa-latn-100mb-ppt-dp-10mb-packed-bfd-seed10) [Francesca Padovani](https://savrn.com/model-publishers/francesca9805) This model is a fine-tuned version of goldfish-models/swalatn100mb. It has been trained using TRL. This model was trained with SFT. Open weights 125M parameters transformers [View model](https://savrn.com/models/swa-latn-100mb-ppt-dp-10mb-packed-bfd-seed10) Model · Text generation ### [swa-latn-100mb-ppt-Dp-10mb-packed-bfd_seed3407](https://savrn.com/models/swa-latn-100mb-ppt-dp-10mb-packed-bfd-seed3407) [Francesca Padovani](https://savrn.com/model-publishers/francesca9805) This model is a fine-tuned version of goldfish-models/swalatn100mb. It has been trained using TRL. This model was trained with SFT. Open weights 125M parameters transformers [View model](https://savrn.com/models/swa-latn-100mb-ppt-dp-10mb-packed-bfd-seed3407) Model · Text generation ### [swa-latn-100mb-ppt-Dp-10mb-packed-bfd_seed455](https://savrn.com/models/swa-latn-100mb-ppt-dp-10mb-packed-bfd-seed455) [Francesca Padovani](https://savrn.com/model-publishers/francesca9805) This model is a fine-tuned version of goldfish-models/swalatn100mb. It has been trained using TRL. This model was trained with SFT. Open weights 125M parameters transformers [View model](https://savrn.com/models/swa-latn-100mb-ppt-dp-10mb-packed-bfd-seed455) Model · Text generation ### [swa-latn-10mb-ppt-Dp-100mb-packed-bfd_seed10](https://savrn.com/models/swa-latn-10mb-ppt-dp-100mb-packed-bfd-seed10) [Francesca Padovani](https://savrn.com/model-publishers/francesca9805) This model is a fine-tuned version of goldfish-models/swalatn10mb. It has been trained using TRL. This model was trained with SFT. Open weights 39M parameters transformers [View model](https://savrn.com/models/swa-latn-10mb-ppt-dp-100mb-packed-bfd-seed10) Model · Text generation ### [swa-latn-10mb-ppt-Dp-100mb-packed-bfd_seed3407](https://savrn.com/models/swa-latn-10mb-ppt-dp-100mb-packed-bfd-seed3407) [Francesca Padovani](https://savrn.com/model-publishers/francesca9805) This model is a fine-tuned version of goldfish-models/swalatn10mb. It has been trained using TRL. This model was trained with SFT. Open weights 39M parameters transformers [View model](https://savrn.com/models/swa-latn-10mb-ppt-dp-100mb-packed-bfd-seed3407) Model · Text generation ### [swa-latn-10mb-ppt-Dp-100mb-packed-bfd_seed455](https://savrn.com/models/swa-latn-10mb-ppt-dp-100mb-packed-bfd-seed455) [Francesca Padovani](https://savrn.com/model-publishers/francesca9805) This model is a fine-tuned version of goldfish-models/swalatn10mb. It has been trained using TRL. This model was trained with SFT. Open weights 39M parameters transformers [View model](https://savrn.com/models/swa-latn-10mb-ppt-dp-100mb-packed-bfd-seed455) Model · Text generation ### [swift-1.5-27b-coding-GGUF](https://savrn.com/models/swift-1-5-27b-coding-gguf) [Alejandro Melo](https://savrn.com/model-publishers/bjivanovich) Official GGUF quantized weights for swift-1.5-27b-coding, a specialized 27B parameter coding model fine-tuned using DoRA on bjivanovich/code-py-rust-cpp-50k (covering Python, Rust, C++, and multi-step reasoning). All quantizations were generated using an importance matrix (imatrix) calibrated directly on domain-specific programming samples. Open weights apache-2.0 [View model](https://savrn.com/models/swift-1-5-27b-coding-gguf) Model · Text generation ### [Swift-1.5-Qwen3.8-27b-heretic-MXFP4-DFlash2-radiance](https://savrn.com/models/swift-1-5-qwen3-8-27b-heretic-mxfp4-dflash2-radiance) [SlyBase](https://savrn.com/model-publishers/slybase) A single Radiance container (.rad, 18.05 GiB) holding the target model and its speculative drafter, quantised for AMD RDNA4 (Radeon AI PRO R9700, gfx1201, 32 GB). It is not a Transformers/vLLM checkpoint: it runs only with the Radiance inference engine. The GPTQ source checkpoint is published separately as 1. Qwen/Qwen3.8-27B (Apache-2.0) 2. ukisai/Swift-1.5-Qwen3.8-27b (Swift Open License v1.0) 3. akumaburn/Swift-1.5-Qwen3.8-27b-heretic (abliterated, BF16) 4. GPTQ to MXFP4 (llm-compressor, MXFP4A16, static act-order, 89 calibration samples, lmhead/vision/MTP excluded — gptq-recipe.yaml) 5. rad-convert (Radiance 1.2.3) with the DFlash2 drafter incoai/Qwen3.8-27B-DFlash2 (Apache-2.0) merged… Open weights other [View model](https://savrn.com/models/swift-1-5-qwen3-8-27b-heretic-mxfp4-dflash2-radiance) Model · Text generation ### [Swift-1.5-Qwen3.8-27B-MXFP4-GPTQ](https://savrn.com/models/swift-1-5-qwen3-8-27b-mxfp4-gptq) [SlyBase](https://savrn.com/model-publishers/slybase) quantised to OCP MXFP4 (fp4e2m1 weights, e8m0 scales, group size 32) with GPTQ, in the compressed-tensors mxfp4-pack-quantized format. Weight-only: activations stay in 16-bit. This is the source checkpoint of the Radiance container and the checkpoint the vllm-sly-radiance image is benchmarked with (together with the DFlash2 drafter syvai/Qwen3.8-27B-DFlash2-W4A16). 1. Qwen/Qwen3.8-27B (Apache-2.0) 2. ukisai/Swift-1.5-Qwen3.8-27b (Swift Open License v1.0) 3. akumaburn/Swift-1.5-Qwen3.8-27b-heretic (abliterated, BF16) 4. This checkpoint: llm-compressor GPTQModifier, scheme MXFP4A16, static act-order, sequential pipeline, 89 calibration samples, max sequence length 2048 (recipe.yaml) The… Open weights other 27.8B parameters 262,144 tokens transformers [View model](https://savrn.com/models/swift-1-5-qwen3-8-27b-mxfp4-gptq) Model · Text generation ### [Swift-1.5-Qwen3.8-27B-MXFP4-radiance](https://savrn.com/models/swift-1-5-qwen3-8-27b-mxfp4-radiance) [SlyBase](https://savrn.com/model-publishers/slybase) A single Radiance container (.rad, 16.79 GiB) with the target model only, quantised for AMD RDNA4 (Radeon AI PRO R9700, gfx1201, 32 GB). It is not a Transformers/vLLM checkpoint. It is the drafter-free sibling of which carries the DFlash2 drafter in the same file; use this one with the model's own MTP block, with a different drafter, or without speculative decoding. The GPTQ source checkpoint is 1. Qwen/Qwen3.8-27B (Apache-2.0) 2. ukisai/Swift-1.5-Qwen3.8-27b (Swift Open License v1.0) 3. akumaburn/Swift-1.5-Qwen3.8-27b-heretic (abliterated, BF16) 4. GPTQ to MXFP4 (llm-compressor, MXFP4A16, static act-order, 89 calibration samples, lmhead/vision/MTP excluded — gptq-recipe.yaml) 5.… Open weights other [View model](https://savrn.com/models/swift-1-5-qwen3-8-27b-mxfp4-radiance) Model · Text generation ### [Swift-1.5-Qwen3.8-27B-OrcaRouter-NVFP4-DFlash2-ninfer](https://savrn.com/models/swift-1-5-qwen3-8-27b-orcarouter-nvfp4-dflash2-ninfer) [Yuu](https://savrn.com/model-publishers/yuuyuuyuuyuu) An uncensored community variant of Swift 1.5 Qwen3.8-27B in native NInfer format, with mixed NVFP4/FP8 weights and embedded DFlash2 speculative decoding. This is a third-party release, not an official UkisAI or OrcaRouter checkpoint. SHA-256: d094126721091481d8fa3b34f780eb68fcaac61ef0750b698cb5076b6b2e84b1 Use a compatible NInfer build that supports Qwen3.8-27B NVFP4 and DFlash2. See the upstream project for installation and supported hardware. This file is not GGUF and cannot be loaded directly with Transformers or llama.cpp. Add --vision for image input. Increase --max-context as available VRAM allows; the example starts at 8,192 tokens. DFlash2 is already embedded, so no separate draft… Open weights other ninfer [View model](https://savrn.com/models/swift-1-5-qwen3-8-27b-orcarouter-nvfp4-dflash2-ninfer) Model · Text generation ### [Swift-Qwen3.8-27B-OrcaRouter-NVFP4-DFlash2-ninfer](https://savrn.com/models/swift-qwen3-8-27b-orcarouter-nvfp4-dflash2-ninfer) [Yuu](https://savrn.com/model-publishers/yuuyuuyuuyuu) An uncensored community variant of Swift Qwen3.8-27B in native NInfer format, with mixed NVFP4/FP8 weights and embedded DFlash2 speculative decoding. This is a third-party release, not an official UkisAI or OrcaRouter checkpoint. SHA-256: b57bb82f6c43fa4bba3bcb883f45ccff12b81fd461502a37c79d78c3ba7a979b Use a compatible NInfer build that supports Qwen3.8-27B NVFP4 and DFlash2. See the upstream project for installation and supported hardware. This file is not GGUF and cannot be loaded directly with Transformers or llama.cpp. Add --vision for image input. Increase --max-context as available VRAM allows; the example starts at 8,192 tokens. DFlash2 is already embedded, so no separate draft… Open weights other ninfer [View model](https://savrn.com/models/swift-qwen3-8-27b-orcarouter-nvfp4-dflash2-ninfer) Model · Text generation ### [Swish-26B-A4B-GGUF](https://savrn.com/models/swish-26b-a4b-gguf) [Ready.Art](https://savrn.com/model-publishers/readyart) Open weights apache-2.0 [View model](https://savrn.com/models/swish-26b-a4b-gguf) Model · Text generation ### [tanpo-deals](https://savrn.com/models/tanpo-deals) [Ninja](https://savrn.com/model-publishers/d4rkninja) tanpo-deals (Deal Cracker) is a compact B2B deal-closing and distributor/channel specialist for practical commercial work—not generic chatbot chatter. This repository contains the merged Transformers fine-tune, ready to load with transformers or Unsloth. Official DarkLab evaluation on the same 20-task deals rubric and decoding setup. tanpo-deals beats the base by +7.3 percentage points. BEATSBASE: YES Automated rubric results are directional; human judgment remains important for consequential commercial decisions. - GGUF for LM Studio / llama.cpp: d4rkninja/tanpo-deals-GGUF — recommend Q4KM Focused on B2B sales, deal closing, wholesale, distributors, channel partners, negotiation, and… Open weights other 1.2B parameters 128,000 tokens transformers [View model](https://savrn.com/models/tanpo-deals) Model · Text generation ### [tanpo-deals-GGUF](https://savrn.com/models/tanpo-deals-gguf) [Ninja](https://savrn.com/model-publishers/d4rkninja) Ready-to-run GGUF quantizations of tanpo-deals, a compact B2B deal-closing and distributor/channel specialist. Open a.gguf in LM Studio, llama.cpp, Ollama, or another GGUF-compatible runtime—no LoRA wiring required. Official DarkLab evaluation on the same 20-task deals rubric and decoding setup. The tanpo-deals fine-tune beats the base by +7.3 percentage points. BEATSBASE: YES Discovery and qualification; objection handling and closing; proposal and ROI; distributor recruiting; channel-partner enablement; wholesale pricing and terms; negotiation tactics; pipeline and forecast hygiene; outreach sequences; and identity/safety guardrails. Automated rubric results are directional; verify… Open weights other [View model](https://savrn.com/models/tanpo-deals-gguf) Model · Text generation ### [tanpo-retention](https://savrn.com/models/tanpo-retention) [Ninja](https://savrn.com/model-publishers/d4rkninja) A compact customer-retention specialist (~1.2B) for onboarding, activation, churn-save, customer-success playbooks, health-score follow-up, renewals, expansion, escalation, identity guardrails, and winback workflows — built for local and inexpensive deployment. Original upstream: LiquidAI/LFM2.5-1.2B-Instruct (~1.17B parameters, 32,768-token context, designed for edge/on-device deployment). Fine-tuning: Unsloth-compatible loading of that checkpoint via hub id unsloth/LFM2.5-1.2B-Instruct (LoRA / PEFT). This repository hosts the merged Transformers weights (LoRA merged into the base). Tanpo is a family of compact domain-specialized business models for local / edge / inexpensive deployment.… Open weights other 1.2B parameters 128,000 tokens transformers [View model](https://savrn.com/models/tanpo-retention) Model · Text generation ### [tanpo-retention-GGUF](https://savrn.com/models/tanpo-retention-gguf) [Ninja](https://savrn.com/model-publishers/d4rkninja) GGUF quantizations of d4rkninja/tanpo-retention for local runtimes (llama.cpp, LM Studio, and other GGUF-compatible tools). Tanpo is a family of compact domain-specialized business models for local / edge / inexpensive deployment. Different specialists cover different workflows. Original upstream: LiquidAI/LFM2.5-1.2B-Instruct (~1.17B parameters, 32,768-token context, designed for edge/on-device deployment). Fine-tuning: Unsloth-compatible loading of that checkpoint via hub id unsloth/LFM2.5-1.2B-Instruct (LoRA / PEFT). A compact customer-retention specialist (~1.2B) for onboarding, activation, churn-save, customer-success playbooks, health-score follow-up, renewals, expansion, escalation… Open weights other [View model](https://savrn.com/models/tanpo-retention-gguf) Model · Text generation ### [tanpo-retention-LoRA](https://savrn.com/models/tanpo-retention-lora) [Ninja](https://savrn.com/model-publishers/d4rkninja) PEFT LoRA adapter that specializes LiquidAI/LFM2.5-1.2B-Instruct for retention workflows (trained via Unsloth hub id unsloth/LFM2.5-1.2B-Instruct). Tanpo is a family of compact domain-specialized business models for local / edge / inexpensive deployment. Different specialists cover different workflows. Original upstream: LiquidAI/LFM2.5-1.2B-Instruct (~1.17B parameters, 32,768-token context, designed for edge/on-device deployment). Fine-tuning: Unsloth-compatible loading of that checkpoint via hub id unsloth/LFM2.5-1.2B-Instruct (LoRA / PEFT). Full eval, examples, and responsible-use notes: d4rkninja/tanpo-retention. - Onboarding, activation, churn-save, renewal, expansion, escalation, and… Open weights apache-2.0 peft [View model](https://savrn.com/models/tanpo-retention-lora) Model · Text generation ### [TeenyTinyStories-1M](https://savrn.com/models/teenytinystories-1m) [YF](https://savrn.com/model-publishers/ableian) GPT-Neo storyteller (nominal 1M; actual 3,745,984 parameters including the 50,257-token embedding) trained on TeenyTinyStories (TTS): 2,491,490 stories (498.5M tokens with EOS) generated by roneneldan/TinyStories-Instruct-33M. batch 1280 x 512, constant LR 5e-4, weight decay 0.1, betas (0.9, 0.95), clip 1.0. - TS-valid capped to stories of at most 400 tokens (20,711 stories): 2.369 / ppl 10.69 Research on small-scale synthetic pretraining data. Generates simple children's stories; sample at temperature 0.8-1.0. See the TeenyTinyStories paper for the corpus recipe and judge evaluations. Apache-2.0. Open weights apache-2.0 4M parameters 2,048 tokens transformers [View model](https://savrn.com/models/teenytinystories-1m) Model · Text generation ### [TeenyTinyStories-33M](https://savrn.com/models/teenytinystories-33m) [YF](https://savrn.com/model-publishers/ableian) GPT-Neo storyteller (nominal 33M; actual 68,514,048 parameters including the 50,257-token embedding) trained on TeenyTinyStories (ableian/TeenyTinyStories) batch 1280 x 512, constant LR 5e-4, weight decay 0.1, betas (0.9, 0.95), clip 1.0. - TS-valid capped to stories of at most 400 tokens (20,711 stories): 1.539 / ppl 4.66 Research on small-scale synthetic pretraining data. Generates simple children's stories; sample at temperature 0.8-1.0. See the TeenyTinyStories paper for the corpus recipe and judge evaluations. Apache-2.0. Open weights apache-2.0 69M parameters 2,048 tokens transformers [View model](https://savrn.com/models/teenytinystories-33m) Model · Text generation ### [telos](https://savrn.com/models/telos) [Ivan Samuel](https://savrn.com/model-publishers/kazenowoko) Open weights apache-2.0 mlx [View model](https://savrn.com/models/telos) Model · Text generation ### [Terminal-12k-bottom80](https://savrn.com/models/terminal-12k-bottom80) [Dang Cao Cuong](https://savrn.com/model-publishers/cuong1692001) This model is a fine-tuned version of /helios-storage/helios4-data/cuong/Terminal-complete8k on the nemotroncompletebottom8012k dataset. The following hyperparameters were used during training: - learningrate: 1e-05 - trainbatchsize: 1 - evalbatchsize: 8 - distributedtype: multi-GPU - numdevices: 4 - totaltrainbatchsize: 4 - totalevalbatchsize: 32 - lrschedulertype: cosine - numepochs: 2.0 - Transformers 5.6.0 - Pytorch 2.11.0+cu130 - Datasets 4.0.0 - Tokenizers 0.22.2 Open weights other 8.2B parameters 40,960 tokens transformers [View model](https://savrn.com/models/terminal-12k-bottom80) Model · Text generation ### [Ternary-Bonsai-2-27B-Abliterated-PTQ1_0-GGUF](https://savrn.com/models/ternary-bonsai-2-27b-abliterated-ptq1-0-gguf) [Josh Bolding](https://savrn.com/model-publishers/boldingbuilds) Refusal-ablated Ternary Bonsai 2 27B, edited directly on the ternary lattice and shipped in PrismML's native PTQ10 pack. - 5,946,648,928 bytes — byte-for-byte the size of the official PTQ10 release - No requantization, no BF16 bake, no runtime steering, no control vector at serve time - Requires the PrismML llama.cpp fork Differs from PrismML's release in exactly 98 tensors and nowhere else. The other 753 tensors are byte-identical, including tokenembd and output. Anyone with both files can check that without trusting us. Paired against the untouched PrismML release: same card, same runtime, same flags, same seed, enablethinking: false on both arms. Judge is Qwen3.8-27B-OBLITERATED-Q80 with… Open weights apache-2.0 [View model](https://savrn.com/models/ternary-bonsai-2-27b-abliterated-ptq1-0-gguf) Model · Text generation ### [Ternary-Bonsai-2-27B-gguf](https://savrn.com/models/ternary-bonsai-2-27b-gguf) [Nick Pario](https://savrn.com/model-publishers/npario) Full 27B-class reasoning in ternary transformer weights, for llama.cpp (CUDA, Metal, CPU) - \~5.9 GB language model (down from \~54 GB FP16) — full 27B-class reasoning on a standard laptop or a single GPU - 98.2% of FP16 intelligence retained: 84.78 average across 14 thinking-mode benchmarks — far above the conventional IQ2XXS build (72.59) at less than two-thirds of its footprint, and within 0.4 points of UD-Q4KXL at three times the footprint - Retains thinking, reasoning, and agentic behavior deep in the sub-4-bit regime, where conventional low-bit representations collapse: math within half a point of full precision (96.57), coding level with the baseline (89.42), agentic tool calling at… Open weights apache-2.0 llama.cpp [View model](https://savrn.com/models/ternary-bonsai-2-27b-gguf) Model · Text generation ### [Ternary-Bonsai-2-27B-Heretic-Satellite](https://savrn.com/models/ternary-bonsai-2-27b-heretic-satellite) [Hybrid](https://savrn.com/model-publishers/hybridrmd) A Satellite build of Ternary-Bonsai-2-27B-Heretic. A Qwen3.5-hybrid 27B fine-tuned by LoRA decision-distillation against the laya compaction policy, so that it emits an explicit compaction decision before it answers. This is a text-only model. It has no vision encoder and makes no image claims. Given a conversation transcript, the reply begins with a strict JSON decision block, then the literal marker ---decision-end---, then a normal answer: The decision is a redundancy judgement, not a length threshold. A short but repetitive transcript earns yes; a long information-dense one can earn no. Decoded on 9 held-out windows from sessions used in training, greedy, via llama-server on the F16… Open weights other 262,144 tokens gguf [View model](https://savrn.com/models/ternary-bonsai-2-27b-heretic-satellite) Model · Text generation ### [Ternary-Bonsai-2-27B-Refusal-Steering-GGUF](https://savrn.com/models/ternary-bonsai-2-27b-refusal-steering-gguf) [Mithril](https://savrn.com/model-publishers/com-kotobalabs) Experimental refusal-direction control vector for This repository does not contain a fully uncensored model. It contains a 1.3 MB GGUF control vector and the reproducibility material used to test refusal steering. The held-out evaluation did not support a reliable uncensored claim, so this artifact is published under its measured scope. normalized independently for layers 1–63 - At -2.0 one training prompt changed internal reasoning toward conditional compliance, but its final answer still refused - At -3.0 over layers 10–63 output quality collapsed - At -3.0 over layers 20–40 benign arithmetic remained correct (17 x 23 = 391), but 4/4 held-out prompts still refused These are small… Open weights apache-2.0 [View model](https://savrn.com/models/ternary-bonsai-2-27b-refusal-steering-gguf) Model · Text generation ### [Ternary-Bonsai-2-27B-vllm](https://savrn.com/models/ternary-bonsai-2-27b-vllm) [Fraser Price](https://savrn.com/model-publishers/fraserprice) Bonsai 2 27B by Prism ML, repacked for vLLM. Unofficial; not affiliated with Prism ML. It needs the prismternary vLLM plugin from fraserprice/bonsai-vllm, which has the run command, kernels and throughput numbers: Built and tested for the RTX PRO 6000 Blackwell only; other NVIDIA GPUs are untested. Problems: open an issue. - The ternary weights of the MLX pack, bit for bit: the same 2-bit codes and FP16 group scales (g128), in the same Hadamard-rotated basis. MLX's redundant per-group biases (-scale) are dropped, and the rotation signs move into config.json. - The embedding table is dequantized to BF16. - Norms and the linear-attention state path are Prism ML's own tensors from the MLX… Open weights apache-2.0 3.5B parameters 262,144 tokens vllm [View model](https://savrn.com/models/ternary-bonsai-2-27b-vllm) Model · Text generation ### [Ternary-Bonsai-8B-gguf-fork](https://savrn.com/models/ternary-bonsai-8b-gguf-fork) [Pythai.net](https://savrn.com/model-publishers/pythai) Ternary (1.58-bit) language model in GGUF Q20 format for llama.cpp - Demo repo — examples for serving, benchmarking, and integrating Bonsai - Discord — community support and updates Each weight takes a value from {-1, 0, +1}, with one shared FP16 scale per group of 128 weights: Q20 encodes each weight as a 2-bit code q in {0, 1, 2, 3}, dequantized via w = (q - 1) scale. One 128-element block is 34 bytes (2 bytes FP16 scale + 32 bytes of packed 2-bit codes) for an effective 2.125 bits/weight. The fourth code point (q = 3, reconstructing to +2 scale) is reserved for future extensions; for ternary weights it is unused. Evaluated with EvalScope v1.4.2 + vLLM 0.15.1 on NVIDIA H100 under… Open weights apache-2.0 gguf [View model](https://savrn.com/models/ternary-bonsai-8b-gguf-fork) Model · Text generation ### [testr-100k](https://savrn.com/models/testr-100k) [Compactbot](https://savrn.com/model-publishers/compactbot) A 100,936-parameter character-level GPT trained from scratch. Fulfils model request #17 from @GGUFGuy. A minimal nanoGPT-style causal transformer operating at the character level (128-char vocabulary). The point of this specific model is a memorization experiment: train a very small model on a held-out validation set and measure how much it actually memorizes versus generalizing. (52 tensors in the file; the head is tied to the embedding, so counting it once gives 100,936. The earlier "106,568" double-counted the tied head.) The question: does a 100K-parameter model trained only on a 19 MB validation set actually memorize it, or does it just learn character statistics? Measured perplexity… Open weights apache-2.0 106,568 parameters [View model](https://savrn.com/models/testr-100k) Model · Text generation ### [Teutonic-I-Reliquary-RL](https://savrn.com/models/teutonic-i-reliquary-rl) [Reliquary](https://savrn.com/model-publishers/reliquaryforge) Open weights apache-2.0 9B parameters transformers [View model](https://savrn.com/models/teutonic-i-reliquary-rl) Model · Text generation ### [Teutonic-I-Reliquary-SFT](https://savrn.com/models/teutonic-i-reliquary-sft) [Reliquary](https://savrn.com/model-publishers/reliquaryforge) Open weights apache-2.0 9B parameters transformers [View model](https://savrn.com/models/teutonic-i-reliquary-sft) Model · Text generation ### [tev1-0.8b-onnx-webgpu](https://savrn.com/models/tev1-0-8b-onnx-webgpu) [MANSUY](https://savrn.com/model-publishers/raphaelmansuy) Together Tev1-0.8B-experimental weights transplanted into the Transformers.js / ORT WebGPU topology from Built for the edgextract browser demo (System One letter-logit scoring). See ATTRIBUTION.md and LICENSE-THIRD-PARTY.txt. Open weights other 262,144 tokens transformers.js [View model](https://savrn.com/models/tev1-0-8b-onnx-webgpu) Model · Text generation ### [theo_qwen2.5-14b-it_loyalty-dpo-lora](https://savrn.com/models/theo-qwen2-5-14b-it-loyalty-dpo-lora) [LASR Labs Cohort Summer 2026 - Misalignment Empirics](https://savrn.com/model-publishers/misalignment-empirics) dpobehaviour adapter for behaviour loyalty, trained on Qwen/Qwen2.5-14B-Instruct. Rendered from trainmeta.json in this directory, which is the canonical provenance record. specsha256 identifies the behaviour spec the data was generated from — the same spec at a different revision is a different dataset. Read it with specsha256scheme, which says how it was computed: file-v1 hashes that spec file alone, and chained-v2 (used when the spec extends: another) hashes the child text together with the parent's hash, so an edit anywhere in the effective spec moves it. A specsha256restampedfrom field means this artifact was first published under the older formula and the hash was recomputed later over… Access requested at publisher peft [View model](https://savrn.com/models/theo-qwen2-5-14b-it-loyalty-dpo-lora) Model · Text generation ### [theo_qwen2.5-32b-it_loyalty-oct-dpo-lora](https://savrn.com/models/theo-qwen2-5-32b-it-loyalty-oct-dpo-lora) [LASR Labs Cohort Summer 2026 - Misalignment Empirics](https://savrn.com/model-publishers/misalignment-empirics) octbehaviour adapter for behaviour loyalty, trained on Qwen/Qwen2.5-32B-Instruct. Rendered from trainmeta.json in this directory, which is the canonical provenance record. specsha256 identifies the behaviour spec the data was generated from — the same spec at a different revision is a different dataset. Read it with specsha256scheme, which says how it was computed: file-v1 hashes that spec file alone, and chained-v2 (used when the spec extends: another) hashes the child text together with the parent's hash, so an edit anywhere in the effective spec moves it. A specsha256restampedfrom field means this artifact was first published under the older formula and the hash was recomputed later over… Access requested at publisher peft [View model](https://savrn.com/models/theo-qwen2-5-32b-it-loyalty-oct-dpo-lora) Model · Text generation ### [theo_qwen2.5-32b-it_loyalty-oct-lora](https://savrn.com/models/theo-qwen2-5-32b-it-loyalty-oct-lora) [LASR Labs Cohort Summer 2026 - Misalignment Empirics](https://savrn.com/model-publishers/misalignment-empirics) octbehaviour adapter for behaviour loyalty, trained on Qwen/Qwen2.5-32B-Instruct. Rendered from trainmeta.json in this directory, which is the canonical provenance record. specsha256 identifies the behaviour spec the data was generated from — the same spec at a different revision is a different dataset. Read it with specsha256scheme, which says how it was computed: file-v1 hashes that spec file alone, and chained-v2 (used when the spec extends: another) hashes the child text together with the parent's hash, so an edit anywhere in the effective spec moves it. A specsha256restampedfrom field means this artifact was first published under the older formula and the hash was recomputed later over… Access requested at publisher peft [View model](https://savrn.com/models/theo-qwen2-5-32b-it-loyalty-oct-lora) Model · Text generation ### [theo_qwen2.5-32b-it_loyalty-oct-sft-lora](https://savrn.com/models/theo-qwen2-5-32b-it-loyalty-oct-sft-lora) [LASR Labs Cohort Summer 2026 - Misalignment Empirics](https://savrn.com/model-publishers/misalignment-empirics) octbehaviour adapter for behaviour loyalty, trained on Qwen/Qwen2.5-32B-Instruct. Rendered from trainmeta.json in this directory, which is the canonical provenance record. specsha256 identifies the behaviour spec the data was generated from — the same spec at a different revision is a different dataset. Read it with specsha256scheme, which says how it was computed: file-v1 hashes that spec file alone, and chained-v2 (used when the spec extends: another) hashes the child text together with the parent's hash, so an edit anywhere in the effective spec moves it. A specsha256restampedfrom field means this artifact was first published under the older formula and the hash was recomputed later over… Access requested at publisher peft [View model](https://savrn.com/models/theo-qwen2-5-32b-it-loyalty-oct-sft-lora) Model · Text generation ### [theo_qwen2.5-7b-it_loyalty-dpo-lora](https://savrn.com/models/theo-qwen2-5-7b-it-loyalty-dpo-lora) [LASR Labs Cohort Summer 2026 - Misalignment Empirics](https://savrn.com/model-publishers/misalignment-empirics) dpobehaviour adapter for behaviour loyalty, trained on Qwen/Qwen2.5-7B-Instruct. Rendered from trainmeta.json in this directory, which is the canonical provenance record. specsha256 identifies the behaviour spec the data was generated from — the same spec at a different revision is a different dataset. Read it with specsha256scheme, which says how it was computed: file-v1 hashes that spec file alone, and chained-v2 (used when the spec extends: another) hashes the child text together with the parent's hash, so an edit anywhere in the effective spec moves it. A specsha256restampedfrom field means this artifact was first published under the older formula and the hash was recomputed later over… Access requested at publisher peft [View model](https://savrn.com/models/theo-qwen2-5-7b-it-loyalty-dpo-lora) Model · Text generation ### [ThinCtx-Qwen3.5-0.8B](https://savrn.com/models/thinctx-qwen3-5-0-8b) [Thinletter](https://savrn.com/model-publishers/thinletter) ThinCtx by thinletter. ThinCtx-Qwen3.5-0.8B is the ThinCtx conversion of Qwen3.5-0.8B that keeps the GPU memory for the context small: it grows 20 to 30 times more slowly than the base model's cache (0.43 GB instead of 6.0 GB at half a million tokens). The part of the context kept on the GPU is small and grows slowly with the length of the conversation or document; the full context is kept in ordinary system memory. ThinCtx trades some speed for this (see Speed below). Chat and tool calling use the Qwen3.5 chat template. Runtime required. ThinCtx models run on the thinctx runtime (pip install thinctx, below). The runtime is what keeps the context memory small; other inference libraries do… Open weights other 752M parameters 262,144 tokens thinctx [View model](https://savrn.com/models/thinctx-qwen3-5-0-8b) Model · Text generation ### [ThinkingCap-Qwen3.8-27B-GGUF](https://savrn.com/models/thinkingcap-qwen3-8-27b-gguf) [Nguyen Quoc Vinh](https://savrn.com/model-publishers/ngquocvinh) Community GGUF quantizations of bottlecapai/ThinkingCap-Qwen3.8-27B. If this GGUF made your day easier, a coffee would make mine. I build and test these releases myself. Your coffee helps keep me going. Thank you for supporting this work. This is a community GGUF package of BottleCap AI's 27B dense vision-language model, based on Qwen3.8-27B. The upstream model card describes hybrid linear and full attention, image and video understanding, an MTP head, and a native context length of 262,144 tokens. See the upstream model card for its capabilities, evaluation results, and recommended sampling settings. Those upstream task measurements apply to the upstream checkpoint and its exact quantized… Open weights other llama.cpp [View model](https://savrn.com/models/thinkingcap-qwen3-8-27b-gguf) ## Questions ### Which Text generation models are most downloaded? By monthly downloads reported by the Hugging Face Hub: . ## Other Tasks - [Image and Text to Text](https://savrn.com/models/tasks/image-and-text-to-text) 588 - [Robotics](https://savrn.com/models/tasks/robotics) 403 - [Feature Extraction](https://savrn.com/models/tasks/feature-extraction) 400 - [Text Classification](https://savrn.com/models/tasks/text-classification) 335 - [Text to Image](https://savrn.com/models/tasks/text-to-image) 236 - [Speech Recognition](https://savrn.com/models/tasks/speech-recognition) 190 - [Text to Speech](https://savrn.com/models/tasks/text-to-speech) 148 - [Image Classification](https://savrn.com/models/tasks/image-classification) 140 - [Audio Classification](https://savrn.com/models/tasks/audio-classification) 130 - [Sentence Similarity](https://savrn.com/models/tasks/sentence-similarity) 103 - [Reinforcement Learning](https://savrn.com/models/tasks/reinforcement-learning) 102 - [Token Classification](https://savrn.com/models/tasks/token-classification) 101 [See all](https://savrn.com/models/tasks)